summaryrefslogtreecommitdiffstats
path: root/virt/kvm/assigned-dev.c
blob: ecc4419fadca2f92a37b3e9e3ee4d2acde687479 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
/*
 * Kernel-based Virtual Machine - device assignment support
 *
 * Copyright (C) 2010 Red Hat, Inc. and/or its affiliates.
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/errno.h>
#include <linux/spinlock.h>
#include <linux/pci.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include "irq.h"

static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
						      int assigned_dev_id)
{
	struct list_head *ptr;
	struct kvm_assigned_dev_kernel *match;

	list_for_each(ptr, head) {
		match = list_entry(ptr, struct kvm_assigned_dev_kernel, list);
		if (match->assigned_dev_id == assigned_dev_id)
			return match;
	}
	return NULL;
}

static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
				    *assigned_dev, int irq)
{
	int i, index;
	struct msix_entry *host_msix_entries;

	host_msix_entries = assigned_dev->host_msix_entries;

	index = -1;
	for (i = 0; i < assigned_dev->entries_nr; i++)
		if (irq == host_msix_entries[i].vector) {
			index = i;
			break;
		}
	if (index < 0) {
		printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
		return 0;
	}

	return index;
}

static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
{
	struct kvm_assigned_dev_kernel *assigned_dev;
	int i;

	assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
				    interrupt_work);

	spin_lock_irq(&assigned_dev->assigned_dev_lock);
	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
		struct kvm_guest_msix_entry *guest_entries =
			assigned_dev->guest_msix_entries;
		for (i = 0; i < assigned_dev->entries_nr; i++) {
			if (!(guest_entries[i].flags &
					KVM_ASSIGNED_MSIX_PENDING))
				continue;
			guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING;
			kvm_set_irq(assigned_dev->kvm,
				    assigned_dev->irq_source_id,
				    guest_entries[i].vector, 1);
		}
	} else
		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
			    assigned_dev->guest_irq, 1);

	spin_unlock_irq(&assigned_dev->assigned_dev_lock);
}

static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
{
	unsigned long flags;
	struct kvm_assigned_dev_kernel *assigned_dev =
		(struct kvm_assigned_dev_kernel *) dev_id;

	spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags);
	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
		int index = find_index_from_host_irq(assigned_dev, irq);
		if (index < 0)
			goto out;
		assigned_dev->guest_msix_entries[index].flags |=
			KVM_ASSIGNED_MSIX_PENDING;
	}

	schedule_work(&assigned_dev->interrupt_work);

	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
		disable_irq_nosync(irq);
		assigned_dev->host_irq_disabled = true;
	}

out:
	spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags);
	return IRQ_HANDLED;
}

/* Ack the irq line for an assigned device */
static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
{
	struct kvm_assigned_dev_kernel *dev;
	unsigned long flags;

	if (kian->gsi == -1)
		return;

	dev = container_of(kian, struct kvm_assigned_dev_kernel,
			   ack_notifier);

	kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0);

	/* The guest irq may be shared so this ack may be
	 * from another device.
	 */
	spin_lock_irqsave(&dev->assigned_dev_lock, flags);
	if (dev->host_irq_disabled) {
		enable_irq(dev->host_irq);
		dev->host_irq_disabled = false;
	}
	spin_unlock_irqrestore(&dev->assigned_dev_lock, flags);
}

static void deassign_guest_irq(struct kvm *kvm,
			       struct kvm_assigned_dev_kernel *assigned_dev)
{
	kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier);
	assigned_dev->ack_notifier.gsi = -1;

	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
		    assigned_dev->guest_irq, 0);

	if (assigned_dev->irq_source_id != -1)
		kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
	assigned_dev->irq_source_id = -1;
	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK);
}

/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
static void deassign_host_irq(struct kvm *kvm,
			      struct kvm_assigned_dev_kernel *assigned_dev)
{
	/*
	 * In kvm_free_device_irq, cancel_work_sync return true if:
	 * 1. work is scheduled, and then cancelled.
	 * 2. work callback is executed.
	 *
	 * The first one ensured that the irq is disabled and no more events
	 * would happen. But for the second one, the irq may be enabled (e.g.
	 * for MSI). So we disable irq here to prevent further events.
	 *
	 * Notice this maybe result in nested disable if the interrupt type is
	 * INTx, but it's OK for we are going to free it.
	 *
	 * If this function is a part of VM destroy, please ensure that till
	 * now, the kvm state is still legal for probably we also have to wait
	 * interrupt_work done.
	 */
	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
		int i;
		for (i = 0; i < assigned_dev->entries_nr; i++)
			disable_irq_nosync(assigned_dev->
					   host_msix_entries[i].vector);

		cancel_work_sync(&assigned_dev->interrupt_work);

		for (i = 0; i < assigned_dev->entries_nr; i++)
			free_irq(assigned_dev->host_msix_entries[i].vector,
				 (void *)assigned_dev);

		assigned_dev->entries_nr = 0;
		kfree(assigned_dev->host_msix_entries);
		kfree(assigned_dev->guest_msix_entries);
		pci_disable_msix(assigned_dev->dev);
	} else {
		/* Deal with MSI and INTx */
		disable_irq_nosync(assigned_dev->host_irq);
		cancel_work_sync(&assigned_dev->interrupt_work);

		free_irq(assigned_dev->host_irq, (void *)assigned_dev);

		if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI)
			pci_disable_msi(assigned_dev->dev);
	}

	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK);
}

static int kvm_deassign_irq(struct kvm *kvm,
			    struct kvm_assigned_dev_kernel *assigned_dev,
			    unsigned long irq_requested_type)
{
	unsigned long guest_irq_type, host_irq_type;

	if (!irqchip_in_kernel(kvm))
		return -EINVAL;
	/* no irq assignment to deassign */
	if (!assigned_dev->irq_requested_type)
		return -ENXIO;

	host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK;
	guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK;

	if (host_irq_type)
		deassign_host_irq(kvm, assigned_dev);
	if (guest_irq_type)
		deassign_guest_irq(kvm, assigned_dev);

	return 0;
}

static void kvm_free_assigned_irq(struct kvm *kvm,
				  struct kvm_assigned_dev_kernel *assigned_dev)
{
	kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type);
}

static void kvm_free_assigned_device(struct kvm *kvm,
				     struct kvm_assigned_dev_kernel
				     *assigned_dev)
{
	kvm_free_assigned_irq(kvm, assigned_dev);

	pci_reset_function(assigned_dev->dev);

	pci_release_regions(assigned_dev->dev);
	pci_disable_device(assigned_dev->dev);
	pci_dev_put(assigned_dev->dev);

	list_del(&assigned_dev->list);
	kfree(assigned_dev);
}

void kvm_free_all_assigned_devices(struct kvm *kvm)
{
	struct list_head *ptr, *ptr2;
	struct kvm_assigned_dev_kernel *assigned_dev;

	list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) {
		assigned_dev = list_entry(ptr,
					  struct kvm_assigned_dev_kernel,
					  list);

		kvm_free_assigned_device(kvm, assigned_dev);
	}
}

static int assigned_device_enable_host_intx(struct kvm *kvm,
					    struct kvm_assigned_dev_kernel *dev)
{
	dev->host_irq = dev->dev->irq;
	/* Even though this is PCI, we don't want to use shared
	 * interrupts. Sharing host devices with guest-assigned devices
	 * on the same interrupt line is not a happy situation: there
	 * are going to be long delays in accepting, acking, etc.
	 */
	if (request_irq(dev->host_irq, kvm_assigned_dev_intr,
			0, "kvm_assigned_intx_device", (void *)dev))
		return -EIO;
	return 0;
}

#ifdef __KVM_HAVE_MSI
static int assigned_device_enable_host_msi(struct kvm *kvm,
					   struct kvm_assigned_dev_kernel *dev)
{
	int r;

	if (!dev->dev->msi_enabled) {
		r = pci_enable_msi(dev->dev);
		if (r)
			return r;
	}

	dev->host_irq = dev->dev->irq;
	if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0,
			"kvm_assigned_msi_device", (void *)dev)) {
		pci_disable_msi(dev->dev);
		return -EIO;
	}

	return 0;
}
#endif

#ifdef __KVM_HAVE_MSIX
static int assigned_device_enable_host_msix(struct kvm *kvm,
					    struct kvm_assigned_dev_kernel *dev)
{
	int i, r = -EINVAL;

	/* host_msix_entries and guest_msix_entries should have been
	 * initialized */
	if (dev->entries_nr == 0)
		return r;

	r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr);
	if (r)
		return r;

	for (i = 0; i < dev->entries_nr; i++) {
		r = request_irq(dev->host_msix_entries[i].vector,
				kvm_assigned_dev_intr, 0,
				"kvm_assigned_msix_device",
				(void *)dev);
		if (r)
			goto err;
	}

	return 0;
err:
	for (i -= 1; i >= 0; i--)
		free_irq(dev->host_msix_entries[i].vector, (void *)dev);
	pci_disable_msix(dev->dev);
	return r;
}

#endif

static int assigned_device_enable_guest_intx(struct kvm *kvm,
				struct kvm_assigned_dev_kernel *dev,
				struct kvm_assigned_irq *irq)
{
	dev->guest_irq = irq->guest_irq;
	dev->ack_notifier.gsi = irq->guest_irq;
	return 0;
}

#ifdef __KVM_HAVE_MSI
static int assigned_device_enable_guest_msi(struct kvm *kvm,
			struct kvm_assigned_dev_kernel *dev,
			struct kvm_assigned_irq *irq)
{
	dev->guest_irq = irq->guest_irq;
	dev->ack_notifier.gsi = -1;
	dev->host_irq_disabled = false;
	return 0;
}
#endif

#ifdef __KVM_HAVE_MSIX
static int assigned_device_enable_guest_msix(struct kvm *kvm,
			struct kvm_assigned_dev_kernel *dev,
			struct kvm_assigned_irq *irq)
{
	dev->guest_irq = irq->guest_irq;
	dev->ack_notifier.gsi = -1;
	dev->host_irq_disabled = false;
	return 0;
}
#endif

static int assign_host_irq(struct kvm *kvm,
			   struct kvm_assigned_dev_kernel *dev,
			   __u32 host_irq_type)
{
	int r = -EEXIST;

	if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
		return r;

	switch (host_irq_type) {
	case KVM_DEV_IRQ_HOST_INTX:
		r = assigned_device_enable_host_intx(kvm, dev);
		break;
#ifdef __KVM_HAVE_MSI
	case KVM_DEV_IRQ_HOST_MSI:
		r = assigned_device_enable_host_msi(kvm, dev);
		break;
#endif
#ifdef __KVM_HAVE_MSIX
	case KVM_DEV_IRQ_HOST_MSIX:
		r = assigned_device_enable_host_msix(kvm, dev);
		break;
#endif
	default:
		r = -EINVAL;
	}

	if (!r)
		dev->irq_requested_type |= host_irq_type;

	return r;
}

static int assign_guest_irq(struct kvm *kvm,
			    struct kvm_assigned_dev_kernel *dev,
			    struct kvm_assigned_irq *irq,
			    unsigned long guest_irq_type)
{
	int id;
	int r = -EEXIST;

	if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK)
		return r;

	id = kvm_request_irq_source_id(kvm);
	if (id < 0)
		return id;

	dev->irq_source_id = id;

	switch (guest_irq_type) {
	case KVM_DEV_IRQ_GUEST_INTX:
		r = assigned_device_enable_guest_intx(kvm, dev, irq);
		break;
#ifdef __KVM_HAVE_MSI
	case KVM_DEV_IRQ_GUEST_MSI:
		r = assigned_device_enable_guest_msi(kvm, dev, irq);
		break;
#endif
#ifdef __KVM_HAVE_MSIX
	case KVM_DEV_IRQ_GUEST_MSIX:
		r = assigned_device_enable_guest_msix(kvm, dev, irq);
		break;
#endif
	default:
		r = -EINVAL;
	}

	if (!r) {
		dev->irq_requested_type |= guest_irq_type;
		kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
	} else
		kvm_free_irq_source_id(kvm, dev->irq_source_id);

	return r;
}

/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */
static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
				   struct kvm_assigned_irq *assigned_irq)
{
	int r = -EINVAL;
	struct kvm_assigned_dev_kernel *match;
	unsigned long host_irq_type, guest_irq_type;

	if (!irqchip_in_kernel(kvm))
		return r;

	mutex_lock(&kvm->lock);
	r = -ENODEV;
	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
				      assigned_irq->assigned_dev_id);
	if (!match)
		goto out;

	host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK);
	guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK);

	r = -EINVAL;
	/* can only assign one type at a time */
	if (hweight_long(host_irq_type) > 1)
		goto out;
	if (hweight_long(guest_irq_type) > 1)
		goto out;
	if (host_irq_type == 0 && guest_irq_type == 0)
		goto out;

	r = 0;
	if (host_irq_type)
		r = assign_host_irq(kvm, match, host_irq_type);
	if (r)
		goto out;

	if (guest_irq_type)
		r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type);
out:
	mutex_unlock(&kvm->lock);
	return r;
}

static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
					 struct kvm_assigned_irq
					 *assigned_irq)
{
	int r = -ENODEV;
	struct kvm_assigned_dev_kernel *match;

	mutex_lock(&kvm->lock);

	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
				      assigned_irq->assigned_dev_id);
	if (!match)
		goto out;

	r = kvm_deassign_irq(kvm, match, assigned_irq->flags);
out:
	mutex_unlock(&kvm->lock);
	return r;
}

static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
				      struct kvm_assigned_pci_dev *assigned_dev)
{
	int r = 0, idx;
	struct kvm_assigned_dev_kernel *match;
	struct pci_dev *dev;

	mutex_lock(&kvm->lock);
	idx = srcu_read_lock(&kvm->srcu);

	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
				      assigned_dev->assigned_dev_id);
	if (match) {
		/* device already assigned */
		r = -EEXIST;
		goto out;
	}

	match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL);
	if (match == NULL) {
		printk(KERN_INFO "%s: Couldn't allocate memory\n",
		       __func__);
		r = -ENOMEM;
		goto out;
	}
	dev = pci_get_domain_bus_and_slot(assigned_dev->segnr,
				   assigned_dev->busnr,
				   assigned_dev->devfn);
	if (!dev) {
		printk(KERN_INFO "%s: host device not found\n", __func__);
		r = -EINVAL;
		goto out_free;
	}
	if (pci_enable_device(dev)) {
		printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
		r = -EBUSY;
		goto out_put;
	}
	r = pci_request_regions(dev, "kvm_assigned_device");
	if (r) {
		printk(KERN_INFO "%s: Could not get access to device regions\n",
		       __func__);
		goto out_disable;
	}

	pci_reset_function(dev);

	match->assigned_dev_id = assigned_dev->assigned_dev_id;
	match->host_segnr = assigned_dev->segnr;
	match->host_busnr = assigned_dev->busnr;
	match->host_devfn = assigned_dev->devfn;
	match->flags = assigned_dev->flags;
	match->dev = dev;
	spin_lock_init(&match->assigned_dev_lock);
	match->irq_source_id = -1;
	match->kvm = kvm;
	match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
	INIT_WORK(&match->interrupt_work,
		  kvm_assigned_dev_interrupt_work_handler);

	list_add(&match->list, &kvm->arch.assigned_dev_head);

	if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
		if (!kvm->arch.iommu_domain) {
			r = kvm_iommu_map_guest(kvm);
			if (r)
				goto out_list_del;
		}
		r = kvm_assign_device(kvm, match);
		if (r)
			goto out_list_del;
	}

out:
	srcu_read_unlock(&kvm->srcu, idx);
	mutex_unlock(&kvm->lock);
	return r;
out_list_del:
	list_del(&match->list);
	pci_release_regions(dev);
out_disable:
	pci_disable_device(dev);
out_put:
	pci_dev_put(dev);
out_free:
	kfree(match);
	srcu_read_unlock(&kvm->srcu, idx);
	mutex_unlock(&kvm->lock);
	return r;
}

static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
		struct kvm_assigned_pci_dev *assigned_dev)
{
	int r = 0;
	struct kvm_assigned_dev_kernel *match;

	mutex_lock(&kvm->lock);

	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
				      assigned_dev->assigned_dev_id);
	if (!match) {
		printk(KERN_INFO "%s: device hasn't been assigned before, "
		  "so cannot be deassigned\n", __func__);
		r = -EINVAL;
		goto out;
	}

	if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
		kvm_deassign_device(kvm, match);

	kvm_free_assigned_device(kvm, match);

out:
	mutex_unlock(&kvm->lock);
	return r;
}


#ifdef __KVM_HAVE_MSIX
static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
				    struct kvm_assigned_msix_nr *entry_nr)
{
	int r = 0;
	struct kvm_assigned_dev_kernel *adev;

	mutex_lock(&kvm->lock);

	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
				      entry_nr->assigned_dev_id);
	if (!adev) {
		r = -EINVAL;
		goto msix_nr_out;
	}

	if (adev->entries_nr == 0) {
		adev->entries_nr = entry_nr->entry_nr;
		if (adev->entries_nr == 0 ||
		    adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) {
			r = -EINVAL;
			goto msix_nr_out;
		}

		adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) *
						entry_nr->entry_nr,
						GFP_KERNEL);
		if (!adev->host_msix_entries) {
			r = -ENOMEM;
			goto msix_nr_out;
		}
		adev->guest_msix_entries = kzalloc(
				sizeof(struct kvm_guest_msix_entry) *
				entry_nr->entry_nr, GFP_KERNEL);
		if (!adev->guest_msix_entries) {
			kfree(adev->host_msix_entries);
			r = -ENOMEM;
			goto msix_nr_out;
		}
	} else /* Not allowed set MSI-X number twice */
		r = -EINVAL;
msix_nr_out:
	mutex_unlock(&kvm->lock);
	return r;
}

static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
				       struct kvm_assigned_msix_entry *entry)
{
	int r = 0, i;
	struct kvm_assigned_dev_kernel *adev;

	mutex_lock(&kvm->lock);

	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
				      entry->assigned_dev_id);

	if (!adev) {
		r = -EINVAL;
		goto msix_entry_out;
	}

	for (i = 0; i < adev->entries_nr; i++)
		if (adev->guest_msix_entries[i].vector == 0 ||
		    adev->guest_msix_entries[i].entry == entry->entry) {
			adev->guest_msix_entries[i].entry = entry->entry;
			adev->guest_msix_entries[i].vector = entry->gsi;
			adev->host_msix_entries[i].entry = entry->entry;
			break;
		}
	if (i == adev->entries_nr) {
		r = -ENOSPC;
		goto msix_entry_out;
	}

msix_entry_out:
	mutex_unlock(&kvm->lock);

	return r;
}
#endif

long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
				  unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	int r = -ENOTTY;

	switch (ioctl) {
	case KVM_ASSIGN_PCI_DEVICE: {
		struct kvm_assigned_pci_dev assigned_dev;

		r = -EFAULT;
		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
			goto out;
		r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev);
		if (r)
			goto out;
		break;
	}
	case KVM_ASSIGN_IRQ: {
		r = -EOPNOTSUPP;
		break;
	}
#ifdef KVM_CAP_ASSIGN_DEV_IRQ
	case KVM_ASSIGN_DEV_IRQ: {
		struct kvm_assigned_irq assigned_irq;

		r = -EFAULT;
		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
			goto out;
		r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq);
		if (r)
			goto out;
		break;
	}
	case KVM_DEASSIGN_DEV_IRQ: {
		struct kvm_assigned_irq assigned_irq;

		r = -EFAULT;
		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
			goto out;
		r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq);
		if (r)
			goto out;
		break;
	}
#endif
#ifdef KVM_CAP_DEVICE_DEASSIGNMENT
	case KVM_DEASSIGN_PCI_DEVICE: {
		struct kvm_assigned_pci_dev assigned_dev;

		r = -EFAULT;
		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
			goto out;
		r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev);
		if (r)
			goto out;
		break;
	}
#endif
#ifdef KVM_CAP_IRQ_ROUTING
	case KVM_SET_GSI_ROUTING: {
		struct kvm_irq_routing routing;
		struct kvm_irq_routing __user *urouting;
		struct kvm_irq_routing_entry *entries;

		r = -EFAULT;
		if (copy_from_user(&routing, argp, sizeof(routing)))
			goto out;
		r = -EINVAL;
		if (routing.nr >= KVM_MAX_IRQ_ROUTES)
			goto out;
		if (routing.flags)
			goto out;
		r = -ENOMEM;
		entries = vmalloc(routing.nr * sizeof(*entries));
		if (!entries)
			goto out;
		r = -EFAULT;
		urouting = argp;
		if (copy_from_user(entries, urouting->entries,
				   routing.nr * sizeof(*entries)))
			goto out_free_irq_routing;
		r = kvm_set_irq_routing(kvm, entries, routing.nr,
					routing.flags);
	out_free_irq_routing:
		vfree(entries);
		break;
	}
#endif /* KVM_CAP_IRQ_ROUTING */
#ifdef __KVM_HAVE_MSIX
	case KVM_ASSIGN_SET_MSIX_NR: {
		struct kvm_assigned_msix_nr entry_nr;
		r = -EFAULT;
		if (copy_from_user(&entry_nr, argp, sizeof entry_nr))
			goto out;
		r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr);
		if (r)
			goto out;
		break;
	}
	case KVM_ASSIGN_SET_MSIX_ENTRY: {
		struct kvm_assigned_msix_entry entry;
		r = -EFAULT;
		if (copy_from_user(&entry, argp, sizeof entry))
			goto out;
		r = kvm_vm_ioctl_set_msix_entry(kvm, &entry);
		if (r)
			goto out;
		break;
	}
#endif
	}
out:
	return r;
}

OpenPOWER on IntegriCloud